[PATCH 1/4] Add routines for filenames encoding <local encoding> <-> UTF-8

@@ -919,6 +919,7 @@ extern int user_ident_explicitly_given;
 
 extern const char *git_commit_encoding;
 extern const char *git_log_output_encoding;
+extern const char *git_filenames_local_encoding;
 extern const char *git_mailmap_file;
 
 /* IO helper functions */

@@ -539,6 +539,9 @@ static int git_default_i18n_config(const char *var, const char *value)
 	if (!strcmp(var, "i18n.logoutputencoding"))
 		return git_config_string(&git_log_output_encoding, var, value);
 
+	if (!strcmp(var, "i18n.filenameslocalencoding"))
+	     return git_config_string(&git_filenames_local_encoding, var, value);
+
 	/* Add other config variables here and to Documentation/config.txt. */
 	return 0;
 }

@@ -24,6 +24,7 @@ int warn_ambiguous_refs = 1;
 int repository_format_version;
 const char *git_commit_encoding;
 const char *git_log_output_encoding;
+const char *git_filenames_local_encoding;
 int shared_repository = PERM_UMASK;
 const char *apply_default_whitespace;
 const char *apply_default_ignorewhitespace;

@@ -0,0 +1,82 @@
+#include "utf8.h"
+#include "cache.h"
+
+inline static int is_string_ascii(const char *str)
+{
+	int is_ascii = 1;
+
+	for (; *str && is_ascii; str++)
+		is_ascii &= isascii(*str);
+
+	return is_ascii;
+}
+
+static char *filename_to_utf8(const char *filename)
+{
+	char *out;
+
+	if (is_string_ascii(filename))
+		return NULL;
+
+#ifndef NO_ICONV
+	if (git_filenames_local_encoding && !is_utf8(filename)) {
+		out = reencode_string(filename,
+				      "utf-8", git_filenames_local_encoding);
+#ifdef DEBUG_I18N
+		fprintf(stderr, "Local -> UTF8 encoding: <%s> -> <%s>\n",
+			filename, out);
+#endif
+		return out;
+	} else if (git_filenames_local_encoding && is_utf8(filename)) {
+#ifdef DEBUG_I18N
+		fprintf(stderr,
+			"Filename <%s> is already utf8-encoded, doing nothing...\n",
+			filename);
+#endif
+		return NULL;
+	} else {
+#ifdef DEBUG_I18N
+		fprintf(stderr, "No local encoding set, doing nothing...\n");
+#endif
+		return NULL;
+	}
+#else /* #ifdef NO_ICONV */
+	warning("No iconv support, doing nothing...\n");
+	return NULL;
+#endif
+}
+
+char *filename_to_local(const char *filename)
+{
+	char *out;
+
+	if (is_string_ascii(filename))
+		return NULL;
+
+#ifndef NO_ICONV
+	if (git_filenames_local_encoding && is_utf8(filename)) {
+		out = reencode_string(filename,
+				      git_filenames_local_encoding, "utf-8");
+#ifdef DEBUG_I18N
+		fprintf(stderr, "UTF8 -> local encoding: <%s> -> <%s>\n",
+			filename, out);
+#endif
+		return out;
+	} else if (git_filenames_local_encoding && !is_utf8(filename)) {
+#ifdef DEBUG_I18N
+		fprintf(stderr,
+			"Filename <%s> is already local-encoded, doing nothing...\n",
+			filename);
+#endif
+		return NULL;
+	} else {
+#ifdef DEBUG_I18N
+		fprintf(stderr, "No local encoding set, doing nothing...\n");
+#endif
+		return NULL;
+	}
+#else /* #ifdef NO_ICONV */
+	warning("No iconv support, doing nothing...\n");
+	return NULL;
+#endif
+}

@@ -459,6 +459,7 @@ LIB_H += tree-walk.h
 LIB_H += unpack-trees.h
 LIB_H += userdiff.h
 LIB_H += utf8.h
+LIB_H += io-i18n.h
 LIB_H += wt-status.h
 
 LIB_OBJS += abspath.o

@@ -562,6 +563,7 @@ LIB_OBJS += unpack-trees.o
 LIB_OBJS += usage.o
 LIB_OBJS += userdiff.o
 LIB_OBJS += utf8.o
+LIB_OBJS += io-i18n.o
 LIB_OBJS += walker.o
 LIB_OBJS += wrapper.o
 LIB_OBJS += write_or_die.o

@@ -1,3 +1,4 @@
+#include "io-i18n.h"
 #include "utf8.h"
 #include "cache.h"
 

@@ -80,3 +81,131 @@ char *filename_to_local(const char *filename)
 	return NULL;
 #endif
 }
+
+int stat_i18n(const char *filename, struct stat *buf)
+{
+	int ret;
+	char *out = filename_to_local(filename);
+
+	if (out != NULL) {
+		ret = stat(out, buf);
+		free(out);
+	} else
+		ret = stat(filename, buf);
+	return ret;
+}
+
+int lstat_i18n(const char *filename, struct stat *buf)
+{
+
+	int ret;
+	char *out = filename_to_local(filename);
+
+	if (out != NULL) {
+		ret = lstat(out, buf);
+		free(out);
+	} else
+		ret = lstat(filename, buf);
+	return ret;
+}
+
+DIR *opendir_i18n(const char *dirname)
+{
+	DIR *dir;
+	char *out = filename_to_local(dirname);
+
+	if (out != NULL) {
+		dir = opendir(out);
+		free(out);
+	} else
+		dir = opendir(dirname);
+	return dir;
+}
+
+struct dirent *readdir_i18n(DIR * dirstream)
+{
+	struct dirent *de = readdir(dirstream);
+
+	if (de) {
+		char *out = filename_to_utf8(de->d_name);
+
+		if (out) {
+			int len = strlen(out);
+			if (len >= NAME_MAX) {
+				warning("readdir_i18n: converted dir entry name length exceeds NAME_MAX and will be truncated\n");
+				len = NAME_MAX - 1;
+			}
+			memcpy(de->d_name, out, len);
+			de->d_name[len] = '\0';
+			free(out);
+		}
+		return de;
+	} else
+		return NULL;
+}
+
+int open_i18n(const char *filename, int flags, mode_t mode)
+{
+	int ret;
+	char *out = filename_to_local(filename);
+
+	if (out != NULL) {
+		ret = open(out, flags, mode);
+		free(out);
+	} else
+		ret = open(filename, flags, mode);
+	return ret;
+}
+
+FILE *fopen_i18n(const char *filename, const char *opentype)
+{
+	FILE *file;
+	char *out = filename_to_local(filename);
+
+	if (out != NULL) {
+		file = fopen(out, opentype);
+		free(out);
+	} else
+		file = fopen(filename, opentype);
+	return file;
+}
+
+int chmod_i18n(const char *filename, mode_t mode)
+{
+	int ret;
+	char *out = filename_to_local(filename);
+
+	if (out != NULL) {
+		ret = chmod(out, mode);
+		free(out);
+	} else
+		ret = chmod(filename, mode);
+	return ret;
+}
+
+int link_i18n(const char *oldname, const char *newname)
+{
+	char *old_out = filename_to_local(oldname);
+	char *new_out = filename_to_local(newname);
+	int ret = link(old_out ? old_out : oldname,
+		       new_out ? new_out : newname);
+
+	if (old_out)
+		free(old_out);
+	if (new_out)
+		free(new_out);
+	return ret;
+}
+
+int unlink_i18n(const char *filename)
+{
+	char *out = filename_to_local(filename);
+	int ret;
+
+	if (out) {
+		ret = unlink(out);
+		free(out);
+	} else
+		ret = unlink(filename);
+	return ret;
+}

@@ -0,0 +1,23 @@
+#ifndef GIT_IO_I18N_H
+#define GIT_IO_I18N_H
+
+#define _FILE_OFFSET_BITS 64
+
+#include <sys/stat.h>
+#include <dirent.h>
+#include <stdio.h>
+
+#define DEFAULT_OPEN_MODE 0
+
+char *filename_to_local (const char* filename);
+int stat_i18n(const char *filename, struct stat *buf);
+int lstat_i18n(const char *filename, struct stat *buf);
+DIR* opendir_i18n(const char *dirname);
+struct dirent *readdir_i18n(DIR *dirstream);
+int open_i18n(const char *filename, int flags, mode_t mode);
+FILE *fopen_i18n(const char *filename, const char *opentype);
+int chmod_i18n(const char *filename, mode_t mode);
+int link_i18n(const char *oldname, const char *newname);
+int unlink_i18n(const char *filename);
+
+#endif /* GIT_IO_I18N_H */